IQ3_XXS GGUF models
A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 28129 models have a IQ3_XXS file. Sizes run from 2M to 2450B parameters. The longest trained context is 10240K tokens.
QW
X Coder SFT Qwen2.5 7B
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
QW
Qwen2.5 7B Instruct Abliterated
Qwen · mradermacher
Params7.62B
Context32K
Q4_K_M4.7 GB
LL
Rombos LLM 70b Llama 3.3
Llama · bartowski
Params70.6B
Context128K
Q4_K_M42.5 GB
LL
Llama3.1 8B PlumCode
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
PH
Phi 3 mini 128k instruct
Phi · mmnga
Params3.82B
Context128K
Q4_K_M2.4 GB
EC
Eclipsed Phoenix 26B A4B
Eclipsed · mradermacher
Params25.2B
Context256K
Q4_K_M16.8 GB
QW
Qwen3.5 9B Claude 4.6 HighIQ THINKING HERETIC UNCENSORED
Qwen · mradermacher
Params8.95B
Context256K
Q4_K_M5.6 GB
PH
Phi 3.5 Mini instruct_Uncensored
Phi · mradermacher
Params3.82B
Context128K
Q4_K_M2.4 GB
KO
Kolibri 1
Kolibri · webmp3
Params78B
Context256K
Smallest22.5 GB
BA
BananaMind Translate V3.5 Pro
Bananamind · mradermacher
Params7.46B
Context128K
Q4_K_M5.3 GB
GE
Gemma-4-E2B-It
Gemma · UnitGrief
Params4.65B
Context128K
Q4_K_M3.1 GB
LA
30B Lazarus i1
Lazarus · mradermacher
Params32.5B
Context2K
Q4_K_M19.6 GB
KI
Kisoku 1.6b
Kisoku · mradermacher
Params1.6B
Context128K
Q4_K_M1.0 GB
QW
Qwen3 30B A3B Thinking 2507 Art
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
OC
OculusMind ToolCall 8B v2
Oculusmind · mradermacher
Params8.49B
Context256K
Q4_K_M5.2 GB
MO
Moistral-11B-v5b
Moistral · mradermacher
Params10.7B
Context8K
Q4_K_M6.5 GB
NO
Norobara ZLoss 8x7B i1
Norobara · mradermacher
Params46.7B
Context32K
Q4_K_M28.6 GB
QW
Huihui Qwen3 Omni 30B A3B Thinking Abliterated
Qwen · mradermacher
Params30.5B
Context64K
Q4_K_M18.6 GB
QW
Huihui Qwen3 VL 2B Instruct Abliterated
Qwen · noctrex
Params1.72B
Context256K
Q4_K_M1.1 GB
QW
Qwen3 14B Ft Limo
Qwen · bartowski
Params14.8B
Context40K
Q4_K_M9.0 GB
QW
Qwen3 30B A3B Instruct 2507 Heretic
Qwen · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
DE
Deepseek-R1
DeepSeek · unsloth
Params670B
Context160K
Q4_K_M404.7 GB
GE
Gemma 4 31b It Heretic Ara
Gemma · mradermacher
Params30.7B
Context256K
Q4_K_M18.7 GB
LL
Llama 3.1 WhiteRabbitNeo 2 8B
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
LL
Llama 3.1 8B Instruct Heretic V1 1
Llama · mradermacher
Params8B
Context128K
Q4_K_M4.9 GB
GE
GEITje 7b Uncensored
Geitje · mradermacher
Params7.24B
Context32K
Q4_K_M4.4 GB
HU
HuatuoGPT 3 27B
Huatuogpt · mradermacher
Params27B
Context256K
Q4_K_M16.5 GB
SE
Securecoder 30b Pro v2 Merged
Securecoder · mradermacher
Params30.5B
Context256K
Q4_K_M18.6 GB
IN
Intern S2 397B
InternLM · bartowski
Params403B
Context256K
Q4_K_M254.6 GB
GO
Goetia 26B A4B v1.6
Goetia · mradermacher
Params26B
Context256K
Q4_K_M17.2 GB